{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,8]],"date-time":"2026-10-08T22:21:23Z","timestamp":1791498083155,"version":"4.3.4"},"reference-count":25,"publisher":"BMJ","issue":"1","funder":[{"name":"Spotlight Pathology Ltd"}],"content-domain":{"domain":["bmj.com"],"crossmark-restriction":true},"short-container-title":["J Clin Pathol"],"accepted":{"date-parts":[[2023,10,18]]},"published-print":{"date-parts":[[2025,1]]},"abstract":"<jats:sec>\n                    <jats:title>Aims<\/jats:title>\n                    <jats:p>In routine diagnosis of lymphoma, initial non-specialist triage is carried out when the sample is biopsied to determine if referral to specialised haematopathology services is needed. This places a heavy burden on pathology services, causes delays and often results in over-referral of benign cases. We aimed to develop an automated triage system using artificial intelligence (AI) to enable more accurate and rapid referral of cases, thereby addressing these issues.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective dataset of H&amp;E-stained whole slide images (WSI) of lymph nodes was taken from Newcastle University Hospital (302 cases) and Manchester Royal Infirmary Hospital (339 cases) with approximately equal representation of the 3 most prevalent lymphoma subtypes: follicular lymphoma, diffuse large B-cell and classic Hodgkin\u2019s lymphoma, as well as reactive controls. A subset (80%) of the data was used for training, a further validation subset (10%) for model selection and a final non-overlapping test subset (10%) for clinical evaluation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>AI triage achieved multiclass accuracy of 0.828\u00b10.041\u2009and overall accuracy of 0.932\u00b10.024\u2009when discriminating between reactive and malignant cases. Its ability to detect lymphoma was equivalent to that of two haematopathologists (0.925, 0.950) and higher than a non-specialist pathologist (0.75) repeating the same task. To aid explainability, the AI tool also provides uncertainty estimation and attention heatmaps.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Automated triage using AI holds great promise in contributing to the accurate and timely diagnosis of lymphoma, ultimately benefiting patient care and outcomes.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1136\/jcp-2023-209186","type":"journal-article","created":{"date-parts":[[2023,11,9]],"date-time":"2023-11-09T13:20:36Z","timestamp":1699536036000},"page":"28-33","update-policy":"https:\/\/doi.org\/10.1136\/crossmarkpolicy","source":"Crossref","is-referenced-by-count":4,"title":["Lymphoma triage from H&amp;E using AI for improved clinical management"],"prefix":"10.1136","volume":"78","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6500-5898","authenticated-orcid":false,"given":"Anna Maria","family":"Tsakiroglou","sequence":"first","affiliation":[{"name":"Spotlight Pathology Ltd, Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chris M","family":"Bacon","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Newcastle University, Newcastle upon Tyne, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Shingleton","sequence":"additional","affiliation":[{"name":"Division of Laboratory Medicine, Manchester University NHS Foundation Trust, Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gabrielle","family":"Slavin","sequence":"additional","affiliation":[{"name":"Department of Cellular Pathology, Manchester University NHS Foundation Trust, Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prokopios","family":"Vogiatzis","sequence":"additional","affiliation":[{"name":"Cellular Pathology Department, Southend University Hospital, Mid & South Essex NHS Trust, Essex, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Byers","sequence":"additional","affiliation":[{"name":"Spotlight Pathology Ltd, Manchester, UK"},{"name":"Department of Histopathology, Manchester University NHS Foundation Trust, Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Carey","sequence":"additional","affiliation":[{"name":"Translational and Clinical Research Institute, Newcastle University, Newcastle upon Tyne, UK"},{"name":"Haematology, Newcastle Upon Tyne Hospitals NHS Foundation Trust, Newcastle Upon Tyne, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Martin","family":"Fergie","sequence":"additional","affiliation":[{"name":"Spotlight Pathology Ltd, Manchester, UK"},{"name":"School of Health Sciences, Faculty of Medicine, Biology and Health, The University of Manchester, Manchester, UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"239","published-online":{"date-parts":[[2023,11,9]]},"reference":[{"key":"2025120519054027000_78.1.28.1","unstructured":"Cancer Research UK . Statistics by cancer type. 2023. Available: https:\/\/www.cancerresearchuk.org\/health-professional\/cancer-statistics\/statistics-by-cancer-type"},{"key":"2025120519054027000_78.1.28.2","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.34163"},{"key":"2025120519054027000_78.1.28.3","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.33948"},{"key":"2025120519054027000_78.1.28.4","unstructured":"Leukemia & Lymphoma Society . Facts 2020-2021. n.d. Available: https:\/\/www.lls.org\/lymphoma"},{"key":"2025120519054027000_78.1.28.5","unstructured":"Haematological cancers: improving outcomes [NICE Guideline no.47]. 2016. Available: https:\/\/www.nice.org.uk\/guidance\/NG47"},{"key":"2025120519054027000_78.1.28.6","doi-asserted-by":"publisher","DOI":"10.1158\/1055-9965.EPI-15-0921"},{"key":"2025120519054027000_78.1.28.7","doi-asserted-by":"publisher","DOI":"10.1093\/jnci\/djaa194"},{"key":"2025120519054027000_78.1.28.8","doi-asserted-by":"crossref","DOI":"10.4103\/jpi.jpi_16_20","article-title":"Is the time right to start using digital pathology and artificial intelligence for the diagnosis of lymphoma","volume":"11","author":"Salama","year":"2020","journal-title":"J Pathol Inform"},{"key":"2025120519054027000_78.1.28.9","doi-asserted-by":"crossref","DOI":"10.4103\/2153-3539.186902","article-title":"Deep learning for digital pathology image analysis: a comprehensive tutorial with selected use cases","volume":"7","author":"Janowczyk","year":"2016","journal-title":"J Pathol Inform"},{"key":"2025120519054027000_78.1.28.10","first-page":"153","article-title":"Automated diagnosis of lymphoma with Digital pathology images using deep learning","volume":"49","author":"El Achi","year":"2019","journal-title":"Ann Clin Lab Sci"},{"key":"2025120519054027000_78.1.28.11","doi-asserted-by":"crossref","unstructured":"Hashimoto N , Fukushima D , Koga R , et al . Multi-scale domain-adversarial multiple-instance CNN for cancer subtype classification with unannotated histopathological images. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2020: 3852\u201361.","DOI":"10.1109\/CVPR42600.2020.00391"},{"key":"2025120519054027000_78.1.28.12","doi-asserted-by":"crossref","DOI":"10.3390\/cancers13102419","article-title":"Deep learning for the classification of non-Hodgkin lymphoma on histopathological images","volume":"13","author":"Steinbuss","year":"2021","journal-title":"Cancers (Basel)"},{"key":"2025120519054027000_78.1.28.13","doi-asserted-by":"publisher","DOI":"10.1093\/ajcp\/aqaa001"},{"key":"2025120519054027000_78.1.28.14","doi-asserted-by":"crossref","unstructured":"Khelil H , El Moumene Zerari A , Djerou L . Accurate diagnosis of non-Hodgkin lymphoma on whole-slide images using deep learning. In: 2022 IEEE 9th International Conference on Sciences of Electronics, Technologies of Information and Telecommunications (SETIT). Hammamet, Tunisia: IEEE, 2022: 447\u201351.","DOI":"10.1109\/SETIT54465.2022.9875482"},{"key":"2025120519054027000_78.1.28.15","doi-asserted-by":"publisher","DOI":"10.1159\/000516589"},{"key":"2025120519054027000_78.1.28.16","doi-asserted-by":"crossref","DOI":"10.1038\/s41746-020-0272-0","article-title":"Accurate diagnosis of lymphoma on whole-slide histopathology images using deep learning","volume":"3","author":"Syrykh","year":"2020","journal-title":"NPJ Digit Med"},{"key":"2025120519054027000_78.1.28.17","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1200\/CCI.18.00157","article-title":"HistoQC: an open-source quality control tool for digital pathology slides","volume":"3","author":"Janowczyk","year":"2019","journal-title":"JCO Clin Cancer Inform"},{"key":"2025120519054027000_78.1.28.18","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-020-00682-w"},{"key":"2025120519054027000_78.1.28.19","unstructured":"Ilse M , Tomczak J , Welling M . Attention-based deep multiple instance learning. In: Proceedings of Machine Learning Research (PMLR). 2018: 2127\u201336."},{"key":"2025120519054027000_78.1.28.20","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102881"},{"key":"2025120519054027000_78.1.28.21","doi-asserted-by":"crossref","unstructured":"Couture HD , Marron JS , Perou CM , et al . Multiple instance learning for heterogeneous images: training a CNN for Histopathology. In: Medical image computing and computer-assisted intervention (MICCAI). 2018: 254\u201362. doi:10.1007\/978-3-030-00934-2","DOI":"10.1007\/978-3-030-00934-2_29"},{"key":"2025120519054027000_78.1.28.22","doi-asserted-by":"crossref","unstructured":"Raju A , Yao J , Haq MM , et al . Graph attention multi-instance learning for accurate colorectal cancer staging. In: Medical image computing and computer-assisted intervention (MICCAI). 2020. doi:10.1007\/978-3-030-59722-1","DOI":"10.1007\/978-3-030-59722-1_51"},{"key":"2025120519054027000_78.1.28.23","doi-asserted-by":"crossref","unstructured":"Wu F , Liu P , Fu B , et al . Deepgcnmil: multi-head attention guided multi-instance learning approach for whole-slide images survival analysis using graph Convolutional networks. In: Proceedings of the 2022 14th International Conference on Machine Learning and Computing. New York, NY, USA: Association for Computing Machinery, 2022: 67\u201373. doi:10.1145\/3529836.3529942","DOI":"10.1145\/3529836.3529942"},{"key":"2025120519054027000_78.1.28.24","unstructured":"Lakshminarayanan B , Pritzel A , Blundell C . Simple and scalable predictive uncertainty estimation using deep ensembles. In: Advances in Neural Information Processing Systems. 2017."},{"key":"2025120519054027000_78.1.28.25","doi-asserted-by":"crossref","unstructured":"Litjens G , Bandi P , Ehteshami Bejnordi B , et al . H&E-stained sentinel lymph node sections of breast cancer patients: the CAMELYON dataset. Gigascience 2018;7. doi:10.1093\/gigascience\/giy065","DOI":"10.1093\/gigascience\/giy065"}],"container-title":["Journal of Clinical Pathology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.1136\/jcp-2023-209186","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T03:05:52Z","timestamp":1764990352000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcp.bmj.com\/lookup\/doi\/10.1136\/jcp-2023-209186"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,9]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12,18]]},"published-print":{"date-parts":[[2025,1]]}},"alternative-id":["10.1136\/jcp-2023-209186"],"URL":"https:\/\/doi.org\/10.1136\/jcp-2023-209186","relation":{},"ISSN":["0021-9746","1472-4146"],"issn-type":[{"value":"0021-9746","type":"print"},{"value":"1472-4146","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,9]]}}}